[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7542EKPD030NFFRB8YG8X17":3,"skill-same:01M7542EKPD030NFFRB8YG8X17":55},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":33,"commitSha":34,"skillDirectory":35,"forksCount":36,"repositoryHtmlUrl":37,"repositoryHomepageUrl":38,"ownerHtmlUrl":39,"ownerBlogUrl":6,"ownerDescription":40,"updatedAt":41,"install":42,"resources":54},"01M7542EKPD030NFFRB8YG8X17","functional-genomics",null,"Candidate gene evidence from perturbation, dependency, resistance,\nsensitivity, viability, or assay-context records.","exon-research\u002Fgenomi","exon-research","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F287072540?v=4","01M754130SK0JVWXNQKF8XANKV","Exon Research","01M754131W4AFK5CDRWT1KHP8X",492,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fexon-research\u002Fgenomi\u002Fblob\u002Fmaster\u002Fskills\u002Ffunctional-genomics\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: functional-genomics\ndescription: |\n  Candidate gene evidence from perturbation, dependency, resistance,\n  sensitivity, viability, or assay-context records.\ntools:\n  - functional_genomics.retrieve_perturbation_records\n  - functional_genomics.query_geo\n  - functional_genomics.import_perturbation_table\n  - functional_genomics.compare_gene_perturbation\n  - research.list_sources\n  - research.record\nmutating: true\n---\n\n# Functional Genomics Perturbation Evidence\n\nRetrieve functional-genomics perturbation evidence for a declared experimental\ncontext plus candidate genes. Screens are one supported perturbation experiment\nsubtype, not the capability name.\n\n## Contract\n\nPerturbation evidence comes from native public retrieval, user-provided local\ntables, reviewed stored research, or explicitly supplied source records. Generic\ngene biology can explain a result, but it should not outrank direct\nperturbation-source evidence.\n\nDirect support is source-verified perturbation evidence. Source records carry\nverified fields or support spans for the requested cell line, perturbation,\nassay\u002Freadout, and candidate gene relationship; broader biology remains\nadjacent or plausibility-only evidence.\n\nNative coverage currently includes BioGRID ORCS when a BioGRID ORCS access key\nis available, DepMap CRISPR gene-effect release tables when a CSV URL or path\nis configured, and bounded NCBI GEO metadata\u002Ftable discovery. GEO's advantage is\nsource discovery for public or published perturbation datasets: SeriesMatrix\nfiles, supplementary tables, and accession-indexed study records that curated\nscreen APIs may not expose for the requested cell line, perturbation, assay, or\nreadout. If native sources cannot be queried, the response makes that coverage\nstate visible rather than weak ranking evidence.\n\n## Tool Flow\n\n1. Extract candidate gene symbols and the requested context: organism, cell\n   line, perturbation, assay, phenotype, resistance, sensitivity, viability, or\n   readout.\n2. Call `functional_genomics.compare_gene_perturbation` for the normal flow. It\n   retrieves native public perturbation records when configured, verifies source\n   records, and returns candidate evidence rows.\n3. Call `functional_genomics.retrieve_perturbation_records` only for explicit\n   native-source inspection, coverage debugging, or source availability review.\n4. Call `functional_genomics.query_geo` when the advantage is public source\n   discovery: the question mentions a published\u002Fpublic screen dataset, study\n   accession, supplementary table, SeriesMatrix-style file, or compare has\n   insufficient BioGRID\u002FDepMap\u002Fstored evidence for a requested perturbation\n   context that likely came from a public study. The user does not need to name\n   GEO. GEO metadata alone is not direct evidence; direct support still requires\n   table-derived, source-verified candidate gene and perturbation-context fields.\n5. If the source is a local CSV\u002FTSV result table, call\n   `functional_genomics.import_perturbation_table` first.\n6. Pass supplied, imported, or retrieved source records to\n   `functional_genomics.compare_gene_perturbation`; it verifies source records\n   before comparing candidate genes.\n7. Use verified perturbation-source evidence when the user asks for only the gene\n   symbol. Audit `decision_evidence` before explaining the result.\n\n`functional_genomics.compare_gene_perturbation` returns evidence rather than a universal\nanswer. If source records do not support an identifier-only answer, do not invent\na gene; state the source gap or gather better source records.\n\n## Source Record Shape\n\n`functional_genomics.compare_gene_perturbation` accepts reviewed source records. Prefer records that\ninclude the source title or URL, named genes, the source-backed finding, source\ntype, and any verified perturbation context such as cell line, perturbation, assay,\nphenotype, readout, PMID, or DOI.\n\nWhen a paper or dataset directly supports the requested perturbation context, include\nthe specific source-backed spans that verify the cell line, perturbation,\nassay\u002Freadout, and gene relationship. Generic pathway or co-mention literature\nshould remain adjacent evidence.\n\nDirect perturbation-source context outranks generic literature or\npathway plausibility only when source-backed fields verify the context. If no\nsource records are supplied, or if records are generic literature without\ncontext verification, the tool cannot fairly make a high-support ranking.\n\n## Cross-Capability Synthesis\n\nA scope-limited result from this capability is not a final user-facing answer\nwhen other Genomi capabilities can contribute orthogonal evidence to the same\nquestion. Returning \"cannot answer\" while applicable capabilities remain\nunexamined is a host-agent failure mode.\n\n## Tools\n\n### functional_genomics.compare_gene_perturbation\n\nCompare candidate genes by verified functional-genomics perturbation experiment evidence.\n\n**Use when**: Retrieves native public perturbation experiment records when configured, verifies source records, and returns candidate-gene evidence rows for the declared perturbation context.\n\n**Why necessary**: Screen and dependency questions need verified perturbation evidence, not inherited-variant or disease association evidence.\n\n**Example prompts**: Which candidate gene is best supported by this CRISPR resistance screen?\n\n**Result semantics**: Runs source-record verification before candidate comparison; generic literature stays separate from direct perturbation experiment evidence.\n\n### functional_genomics.import_perturbation_table\n\nExtract verified perturbation experiment source records from a local CSV or TSV result table.\n\n**Use when**: The agent has a local CSV\u002FTSV perturbation, dependency, viability, resistance, or supplementary result table and needs source records before candidate comparison.\n\n**Why necessary**: User-supplied screen tables need structured extraction before they can support gene comparisons.\n\n**Result semantics**: Extracts table rows into source records and verifies row-level genes plus perturbation context; it does not select the answer gene.\n\n### functional_genomics.query_geo\n\nQuery NCBI GEO metadata and bounded public study tables for functional-genomics perturbation source records.\n\n**Use when**: The advantage is public dataset discovery: a published\u002Fpublic screen, study accession, supplementary table, SeriesMatrix-style file, or an under-covered perturbation context where curated sources did not provide direct source records.\n\n**Why necessary**: GEO can find source-backed tables for study-specific cell lines, perturbations, assays, and readouts that BioGRID ORCS, DepMap, or stored reviewed records may not cover; it keeps metadata-only hits separate from direct perturbation evidence.\n\n**Result semantics**: Returns GEO metadata hits, download candidates with skip reasons, and verified source records when candidate genes are supplied. Metadata-only matches never count as direct evidence; direct support requires source-verified gene plus requested perturbation context fields.\n\n### functional_genomics.retrieve_perturbation_records\n\nRetrieve native public functional-genomics perturbation records from BioGRID ORCS and DepMap for candidate genes and declared experimental context.\n\n**Use when**: Explicit native-source inspection, source availability review, or coverage debugging for BioGRID ORCS and configured DepMap perturbation records.\n\n**Why necessary**: Raw native-source retrieval lets agents inspect what BioGRID ORCS or DepMap returned, or why a native source was unavailable, without running candidate comparison.\n\n**Result semantics**: Returns native functional-genomics source records from BioGRID ORCS and configured DepMap release tables; it does not select the final gene. For normal candidate-gene comparison, use functional_genomics.compare_gene_perturbation directly because it can retrieve native records when configured. BioGRID ORCS requires an access key; DepMap requires a configured public CRISPR gene-effect CSV URL or path.\n","# Functional Genomics Perturbation Evidence\n\nRetrieve functional-genomics perturbation evidence for a declared experimental\ncontext plus candidate genes. Screens are one supported perturbation experiment\nsubtype, not the capability name.\n\n## Contract\n\nPerturbation evidence comes from native public retrieval, user-provided local\ntables, reviewed stored research, or explicitly supplied source records. Generic\ngene biology can explain a result, but it should not outrank direct\nperturbation-source evidence.\n\nDirect support is source-verified perturbation evidence. Source records carry\nverified fields or support spans for the requested cell line, perturbation,\nassay\u002Freadout, and candidate gene relationship; broader biology remains\nadjacent or plausibility-only evidence.\n\nNative coverage currently includes BioGRID ORCS when a BioGRID ORCS access key\nis available, DepMap CRISPR gene-effect release tables when a CSV URL or path\nis configured, and bounded NCBI GEO metadata\u002Ftable discovery. GEO's advantage is\nsource discovery for public or published perturbation datasets: SeriesMatrix\nfiles, supplementary tables, and accession-indexed study records that curated\nscreen APIs may not expose for the requested cell line, perturbation, assay, or\nreadout. If native sources cannot be queried, the response makes that coverage\nstate visible rather than weak ranking evidence.\n\n## Tool Flow\n\n1. Extract candidate gene symbols and the requested context: organism, cell\n   line, perturbation, assay, phenotype, resistance, sensitivity, viability, or\n   readout.\n2. Call `functional_genomics.compare_gene_perturbation` for the normal flow. It\n   retrieves native public perturbation records when configured, verifies source\n   records, and returns candidate evidence rows.\n3. Call `functional_genomics.retrieve_perturbation_records` only for explicit\n   native-source inspection, coverage debugging, or source availability review.\n4. Call `functional_genomics.query_geo` when the advantage is public source\n   discovery: the question mentions a published\u002Fpublic screen dataset, study\n   accession, supplementary table, SeriesMatrix-style file, or compare has\n   insufficient BioGRID\u002FDepMap\u002Fstored evidence for a requested perturbation\n   context that likely came from a public study. The user does not need to name\n   GEO. GEO metadata alone is not direct evidence; direct support still requires\n   table-derived, source-verified candidate gene and perturbation-context fields.\n5. If the source is a local CSV\u002FTSV result table, call\n   `functional_genomics.import_perturbation_table` first.\n6. Pass supplied, imported, or retrieved source records to\n   `functional_genomics.compare_gene_perturbation`; it verifies source records\n   before comparing candidate genes.\n7. Use verified perturbation-source evidence when the user asks for only the gene\n   symbol. Audit `decision_evidence` before explaining the result.\n\n`functional_genomics.compare_gene_perturbation` returns evidence rather than a universal\nanswer. If source records do not support an identifier-only answer, do not invent\na gene; state the source gap or gather better source records.\n\n## Source Record Shape\n\n`functional_genomics.compare_gene_perturbation` accepts reviewed source records. Prefer records that\ninclude the source title or URL, named genes, the source-backed finding, source\ntype, and any verified perturbation context such as cell line, perturbation, assay,\nphenotype, readout, PMID, or DOI.\n\nWhen a paper or dataset directly supports the requested perturbation context, include\nthe specific source-backed spans that verify the cell line, perturbation,\nassay\u002Freadout, and gene relationship. Generic pathway or co-mention literature\nshould remain adjacent evidence.\n\nDirect perturbation-source context outranks generic literature or\npathway plausibility only when source-backed fields verify the context. If no\nsource records are supplied, or if records are generic literature without\ncontext verification, the tool cannot fairly make a high-support ranking.\n\n## Cross-Capability Synthesis\n\nA scope-limited result from this capability is not a final user-facing answer\nwhen other Genomi capabilities can contribute orthogonal evidence to the same\nquestion. Returning \"cannot answer\" while applicable capabilities remain\nunexamined is a host-agent failure mode.\n\n## Tools\n\n### functional_genomics.compare_gene_perturbation\n\nCompare candidate genes by verified functional-genomics perturbation experiment evidence.\n\n**Use when**: Retrieves native public perturbation experiment records when configured, verifies source records, and returns candidate-gene evidence rows for the declared perturbation context.\n\n**Why necessary**: Screen and dependency questions need verified perturbation evidence, not inherited-variant or disease association evidence.\n\n**Example prompts**: Which candidate gene is best supported by this CRISPR resistance screen?\n\n**Result semantics**: Runs source-record verification before candidate comparison; generic literature stays separate from direct perturbation experiment evidence.\n\n### functional_genomics.import_perturbation_table\n\nExtract verified perturbation experiment source records from a local CSV or TSV result table.\n\n**Use when**: The agent has a local CSV\u002FTSV perturbation, dependency, viability, resistance, or supplementary result table and needs source records before candidate comparison.\n\n**Why necessary**: User-supplied screen tables need structured extraction before they can support gene comparisons.\n\n**Result semantics**: Extracts table rows into source records and verifies row-level genes plus perturbation context; it does not select the answer gene.\n\n### functional_genomics.query_geo\n\nQuery NCBI GEO metadata and bounded public study tables for functional-genomics perturbation source records.\n\n**Use when**: The advantage is public dataset discovery: a published\u002Fpublic screen, study accession, supplementary table, SeriesMatrix-style file, or an under-covered perturbation context where curated sources did not provide direct source records.\n\n**Why necessary**: GEO can find source-backed tables for study-specific cell lines, perturbations, assays, and readouts that BioGRID ORCS, DepMap, or stored reviewed records may not cover; it keeps metadata-only hits separate from direct perturbation evidence.\n\n**Result semantics**: Returns GEO metadata hits, download candidates with skip reasons, and verified source records when candidate genes are supplied. Metadata-only matches never count as direct evidence; direct support requires source-verified gene plus requested perturbation context fields.\n\n### functional_genomics.retrieve_perturbation_records\n\nRetrieve native public functional-genomics perturbation records from BioGRID ORCS and DepMap for candidate genes and declared experimental context.\n\n**Use when**: Explicit native-source inspection, source availability review, or coverage debugging for BioGRID ORCS and configured DepMap perturbation records.\n\n**Why necessary**: Raw native-source retrieval lets agents inspect what BioGRID ORCS or DepMap returned, or why a native source was unavailable, without running candidate comparison.\n\n**Result semantics**: Returns native functional-genomics source records from BioGRID ORCS and configured DepMap release tables; it does not select the final gene. For normal candidate-gene comparison, use functional_genomics.compare_gene_perturbation directly because it can retrieve native records when configured. BioGRID ORCS requires an access key; DepMap requires a configured public CRISPR gene-effect CSV URL or path.\n",{"name":5,"tools":24,"mutating":31,"description":32},[25,26,27,28,29,30],"functional_genomics.retrieve_perturbation_records","functional_genomics.query_geo","functional_genomics.import_perturbation_table","functional_genomics.compare_gene_perturbation","research.list_sources","research.record",true,"Candidate gene evidence from perturbation, dependency, resistance,\nsensitivity, viability, or assay-context records.\n","master","1df4f5bfb635e2d08f93a1102b70b840fbe80d86","skills\u002Ffunctional-genomics",61,"https:\u002F\u002Fgithub.com\u002Fexon-research\u002Fgenomi","https:\u002F\u002Fwww.genomiagent.com\u002F","https:\u002F\u002Fgithub.com\u002Fexon-research","Building local-first AI co-scientist for genomic research","2026-09-01 03:30:56",{"source":8,"skillName":5,"commands":43,"prompt":53,"zipAvailable":31},[44,47,50],{"tool":45,"command":46},"npx","npx skills add exon-research\u002Fgenomi --skill functional-genomics",{"tool":48,"command":49},"bunx","bunx skills add exon-research\u002Fgenomi --skill functional-genomics",{"tool":51,"command":52},"pnpm","pnpm dlx skills add exon-research\u002Fgenomi --skill functional-genomics","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fexon-research\u002Fgenomi\u002Fblob\u002Fmaster\u002Fskills\u002Ffunctional-genomics\u002FSKILL.md",[],[56,63,70,77,84,91],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M75442YT3ZG6MG47E5MJ3HG2","variant-evidence","Answer specific rsID, allele, gene, region, genotype, and absence\u002Fcallability\nquestions using explicit session context or public evidence.","https:\u002F\u002Fgithub.com\u002Fexon-research\u002Fgenomi\u002Fblob\u002Fmaster\u002Fskills\u002Fvariant-evidence\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M754400MW6S0MEN19S4CM9DE","journal-source-research","Journal sub-skill for focused public\u002Fsource evidence review and reviewed\nfinding write-back before interpretation or answer synthesis.","https:\u002F\u002Fgithub.com\u002Fexon-research\u002Fgenomi\u002Fblob\u002Fmaster\u002Fskills\u002Fsource-research\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M7543X67TA0MBK3YGC0NJAX9","sequence","Deterministic sequence utilities for translation, ORFs, restriction sites,\nKozak context, primer checks, and local FASTA record matching.","https:\u002F\u002Fgithub.com\u002Fexon-research\u002Fgenomi\u002Fblob\u002Fmaster\u002Fskills\u002Fsequence\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M7543RHCHF4WJ69P0K0QTTFB","rare-disease-cancer","Plan rare disease, hereditary disease, cancer risk, carrier-relevance, and\nobserved-condition source investigation from public targets or selected\nactive genome evidence.","https:\u002F\u002Fgithub.com\u002Fexon-research\u002Fgenomi\u002Fblob\u002Fmaster\u002Fskills\u002Frare-disease-cancer\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M7543NDTVZB8T3RQBD0RK3MC","prs","Apply published polygenic scores from PGS Catalog to approved local personal DNA and return raw weighted score plus overlap QC.","https:\u002F\u002Fgithub.com\u002Fexon-research\u002Fgenomi\u002Fblob\u002Fmaster\u002Fskills\u002Fprs\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":19},"01M7543FDFTWSYVVTEGHQSPHQK","pharmacogenomics","Answer drug-response, medication, PharmGKB-style, PGxDB, ATC, DrugBank,\ngene-drug, and variant-drug questions using public PGx evidence plus local\nsample genotype support when an Active Genome Index is selected.","https:\u002F\u002Fgithub.com\u002Fexon-research\u002Fgenomi\u002Fblob\u002Fmaster\u002Fskills\u002Fpharmacogenomics\u002FSKILL.md",[],[]]